-
公开(公告)号:US10942775B2
公开(公告)日:2021-03-09
申请号:US16289698
申请日:2019-03-01
发明人: Michael A. Blake , Arun Iyengar
摘要: Embodiments includes a computer-implemented method, a system and computer-program product for modifying central serialization of requests in multiprocessor systems. Some embodiments includes receiving an operation requiring resources from a pool of resources, determining an availability of the pool of resources required by the operation, and selecting a queue of a plurality of queues to queue the operation based at least in part on the availability of the pool of resources. Some embodiments also include setting a resource needs register and needs register for the selected queue, and setting a take-two bit for the selected queue.
-
公开(公告)号:US10915461B2
公开(公告)日:2021-02-09
申请号:US16292762
申请日:2019-03-05
发明人: Ekaterina M. Ambroladze , Robert J. Sonnelitter, III , Matthias Klein , Craig Walters , Kevin Lopes , Michael A. Blake , Tim Bronson , Kenneth Klapproth , Vesselina Papazova , Hieu T Huynh
IPC分类号: G06F12/126 , G06F12/084 , G06F12/0811
摘要: Embodiments of the present invention are directed to a computer-implemented method for cache eviction. The method includes detecting a first data in a shared cache and a first cache in response to a request by a first processor. The first data is determined to have a mid-level cache eviction priority. A request is detected from a second processor for a same first data as requested by the first processor. However, in this instance, the second processor has indicated that the same first data has a low-level cache eviction priority. The first data is duplicated and loaded to a second cache, however, the data has a low-level cache eviction priority at the second cache.
-
公开(公告)号:US20180341422A1
公开(公告)日:2018-11-29
申请号:US15603728
申请日:2017-05-24
发明人: Deanna P. Berger , Michael A. Blake , Ashraf Elsharif , Kenneth D. Klapproth , Pak-kin Mak , Robert J. Sonnelitter, III , Guy G. Tracy
IPC分类号: G06F3/06 , G06F12/0893 , G06F12/0842
CPC分类号: G06F12/0842 , G06F12/0893 , G06F2212/62
摘要: An aspect includes interlocking operations in an address-sliced cache system. A computer-implemented method includes determining whether a dynamic memory relocation operation is in process in the address-sliced cache system. Based on determining that the dynamic memory relocation operation is in process, a key operation is serialized to maintain a sequenced order of completion of the key operation across a plurality of slices and pipes in the address-sliced cache system. Based on determining that the dynamic memory relocation operation is not in process, a plurality of key operation requests is allowed to launch across two or more of the slices and pipes in parallel in the address-sliced cache system while ensuring that only one instance of the key operations is in process across all of the slices and pipes at a same time.
-
公开(公告)号:US20180336134A1
公开(公告)日:2018-11-22
申请号:US15598837
申请日:2017-05-18
发明人: Michael A. Blake , Timothy C. Bronson , Ashraf ElSharif , Kenneth D. Klapproth , Vesselina K. Papazova , Guy G. Tracy
IPC分类号: G06F12/0817 , G06F12/0891
CPC分类号: G06F12/0817 , G06F12/0891 , G06F2212/1024 , G06F2212/60 , G06F2212/621
摘要: Embodiments of the present invention are directed to a computer-implemented method for ownership tracking updates across multiple simultaneous operations. A non-limiting example of the computer-implemented method includes receiving, by a cache directory control circuit, a message to update a cache directory entry. The method further includes, in response, updating, by the cache directory control circuit, the cache directory entry, and generating a reverse compare signal including an updated ownership vector of a memory line corresponding to the cache directory entry. The method further includes sending the reverse compare signal to a cache controller associated with the cache directory entry.
-
5.
公开(公告)号:US20180307628A1
公开(公告)日:2018-10-25
申请号:US15496525
申请日:2017-04-25
发明人: Michael A. Blake , Pak-kin Mak , Robert J. Sonnelitter, III , Timothy W. Steele , Gary E. Strait , Poornima P. Sulibele , Guy G. Tracy
IPC分类号: G06F12/14 , G06F12/0891 , G06F13/40
CPC分类号: G06F12/1466 , G06F12/0891 , G06F13/4036 , G06F2212/1052
摘要: A computer implemented method for avoiding false activation of hang avoidance mechanisms of a system is provided. The computer implemented method includes receiving, by a nest of the system, rejects from a processor core of the system. The rejects are issued based on a cache line being locked by the processor core. The computer implemented method includes accumulating the rejects by the nest. The computer implemented method includes determining, by the nest, when an amount of the rejects accumulated by the nest has met or exceeded a programmable threshold. The computer implemented method also includes triggering, by the nest, a global reset to counters of the hang avoidance mechanisms of a system in response to the amount meeting or exceeding the programmable threshold.
-
公开(公告)号:US09703661B2
公开(公告)日:2017-07-11
申请号:US14614841
申请日:2015-02-05
IPC分类号: G06F11/00 , G06F11/30 , G06F12/0891 , G06F11/07 , G06F11/08 , G06F12/0811 , G06F12/128
CPC分类号: G06F11/3037 , G06F11/073 , G06F11/0754 , G06F11/076 , G06F11/079 , G06F11/0793 , G06F11/08 , G06F12/0804 , G06F12/0811 , G06F12/0868 , G06F12/0891 , G06F12/0897 , G06F12/128 , G06F2201/85 , G06F2201/885 , G06F2212/1032 , G06F2212/281 , G06F2212/283 , G06F2212/601 , G06F2212/608 , G06F2212/69
摘要: In an approach for taking corrupt portions of cache offline during runtime, a notification of a section of a cache to be taken offline is received, wherein the section includes one or more sets in one or more indexes of the cache. An indication is associated with each set of the one or more sets in a first index of the one or more indexes, wherein the indication marks the respective set as unusable for future operations. Data is purged from the one or more sets in the first index of the cache. Each set of the one or more sets in the first index is marked as invalid.
-
公开(公告)号:US20130339809A1
公开(公告)日:2013-12-19
申请号:US13788744
申请日:2013-03-07
发明人: Ekaterina M. Ambroladze , Michael A. Blake , Michael Fee , Hieu T. Huynh , Patrick J. Meaney , Arthur J. O'Neill
IPC分类号: G06F11/08
CPC分类号: G06F11/1064 , G06F11/073 , G06F11/076 , G06F11/08 , G11C2029/1204
摘要: Embodiments relate to a computer system for bitline deletion, the system including a cache controller and cache. The system is configured to perform a method including detecting a first error when reading a first cache line, recording a first address of the first error, detecting a second error when reading a second cache line, recording a second address of the second error, comparing first and second bitline addresses, comparing the first and second wordline address, activating a bitline delete mode based on matching first and second bitline addresses and not matching first and second wordline addresses, detecting a third error when reading a third cache line, recording a third bitline address of the third error, comparing the second bitline address to the third bitline address and deleting a location corresponding to the third cache line based on the activated bitline delete mode and matching third and second bitline addresses.
摘要翻译: 实施例涉及用于位线删除的计算机系统,该系统包括高速缓存控制器和高速缓存。 该系统被配置为执行一种方法,包括当读取第一高速缓存线时检测第一错误,记录第一错误的第一地址,在读取第二高速缓存行时检测第二错误,记录第二错误的第二地址,比较 第一和第二位线地址,比较第一和第二字线地址,基于匹配的第一和第二位线地址激活位线删除模式,并且不匹配第一和第二字线地址,在读取第三高速缓存线时检测第三错误,记录第三位线地址 将第二位线地址与第三位线地址进行比较,并且基于激活的位线删除模式和匹配的第三和第二位线地址来删除与第三高速缓存线对应的位置。
-
公开(公告)号:US12050538B2
公开(公告)日:2024-07-30
申请号:US17708785
申请日:2022-03-30
发明人: Robert J. Sonnelitter, III , Ekaterina M. Ambroladze , Timothy Bronson , Michael A. Blake , Tu-An T. Nguyen
IPC分类号: G06F12/0891 , G06F9/38 , G06F12/0811 , G06F12/0817
CPC分类号: G06F12/0891 , G06F9/3816 , G06F12/0811 , G06F12/0824
摘要: Castout handling in a distributed cache topology, including: detecting, by a first cache of a plurality of caches, a cache miss; providing, by the first cache to each other cache of the plurality of caches, a message comprising: data indicating a cache address corresponding to the cache miss; and data indicating a cache line to be evicted.
-
公开(公告)号:US11977486B2
公开(公告)日:2024-05-07
申请号:US17712510
申请日:2022-04-04
发明人: Ashraf ElSharif , Richard Joseph Branciforte , Gregory William Alexander , Deanna Postles Dunn Berger , Timothy Bronson , Aaron Tsai , Taylor J. Pritchard , Markus Kaltenbach , Christian Jacobi , Michael A. Blake
IPC分类号: G06F12/0811
CPC分类号: G06F12/0811 , G06F2212/62
摘要: A computer system includes a processor core and a memory system in signal communication with the processor core. The memory system includes a first cache and a second cache. The first cache is arranged at a first level of a hierarchy in the memory system and is configured to store a plurality of first-cache entries. The second cache is arranged at a second level of the hierarchy that is lower than the first level, and stores a plurality of second-cache entries. The first cache maintains a directory that contains information for each of the first-cache entries. The second cache maintains a shadow pointer directory (SPD) that includes one or more SPD entries that maps each of the first-cache entries to a corresponding second cache entry at a lower-level cache location.
-
公开(公告)号:US10831661B2
公开(公告)日:2020-11-10
申请号:US16380307
申请日:2019-04-10
发明人: Ekaterina M. Ambroladze , Tim Bronson , Robert J. Sonnelitter, III , Deanna P. D. Berger , Chad G. Wilson , Kenneth Douglas Klapproth , Arthur O'Neill , Michael A. Blake , Guy G. Tracy
IPC分类号: G06F12/0815
摘要: Processing simultaneous data requests regardless of active request in the same addressable index of a cache. In response to the cache miss in the given congruence, if the number of other compartments in the given congruence class that have an active operation is less than a predetermined threshold, setting a Do Not Cast Out (DNCO) pending indication for each of the compartments that have an active operation in order to block access to each of the other compartments that have active operations and, if the number of other compartments in the given congruence class that have an active operation is not less than a predetermined threshold, blocking another cache miss from occurring in the compartments of the given congruence class by setting a congruence class block pending indication for the given congruence class in order to block access to each of the other compartments of the given congruence class.
-
-
-
-
-
-
-
-
-